Peter Stone @PeterStone_TX Twitter profile

Last Seen Profiles

@FenelonFallsSS

@iksantension

@CharityDim65663

@europeaseguros

@auto_glam

@PipelinerCRM

@Dan_Dan1616

@helpiliveinque

@Quencywiggins

@ElkyService

@petra_jansa

@Captain_Scales

@CatFem

@MOnoriode14342

@JMGlachant

@bokeplokalmalam

@EthanYogi

@severo_michele

@adityamuchamad

@FrendySarang

@Key76061093

@kouryangelo

@Ramiras11

@BaezaAlcaraz

@SharksMafiaClub

@Lark2Bird

@PierceCountyTV

@yongshuji

@chichidoldan

@mie_janie

@CHTREGER

@JaneJanita

@MarioLasoPereda

@EBSI_umontreal

@SillySock

@Ankitsingh_8824

Peter Stone

@PeterStone_TX

14 days

10 years after DQN, what are deep RL’s impacts on robotics? Which robotic problems have seen the most thrilling real-world successes thanks to DRL? Where do we still need to push the boundaries, and how? Our latest survey explores these questions! Read on for more details. 👇

1

82

446

Peter Stone

@PeterStone_TX

2 months

I'm honored and proud to have been promoted to Chief Scientist of Sony AI, effective today. Looking forward to working with a fantastic worldwide team on several exciting and very ambitious projects!

Sony AI – Unleash Human Imagination and Creativity with AI

Sony AI was established in April 2020 to pursue groundbreaking research in AI and robotics in the realm of entertainment. Our partners are artists, makers and creators from around the world.

ai.sony

27

9

313

Peter Stone

@PeterStone_TX

2 years

A super exciting accomplishment by my Sony AI team. Surely one of the most widespread commercial deployments of reinforcement learning!

GTPlanet

@GTPlanetNews

2 years

GT Sophy arrives in Gran Turismo 7 on PS5! We got an early look at the new AI:

4

47

272

5

42

275

Peter Stone

@PeterStone_TX

1 year

Congratulations to (soon to be) Dr. Ishan Durugkar on the successful defense of his dissertation before an illustrious committee. He’s the 24th Ph.D. graduate from my lab and will soon be joining my team at Sony AI.

3

4

194

Peter Stone

@PeterStone_TX

24 days

The press release:

Sony AI Names Peter Stone as Chief Scientist – Sony AI

TOKYO – July 30, 2024 – Sony AI today named Peter Stone as its new Chief Scientist, among other executive appointments. ...

ai.sony

12

6

159

Peter Stone

@PeterStone_TX

3 years

I can’t express how proud I am of my Sony AI team and all our collaborators on this result of our work over the past 2 years. See the details on today’s issue of Nature!

Sony AI

@SonyAI_global

3 years

What is #GTSophy ? 🏁 GT Sophy is an autonomous #AI agent trained utilizing a novel deep reinforcement learning platform. Our breakthrough research "Outracing Champion Gran Turismo Drivers with Deep Reinforcement Learning" was published today in @Nature .

4

100

290

4

17

142

Peter Stone

@PeterStone_TX

10 months

Congratulations to the whole Sony AI team on what is surely one of the largest ever commercial deployments of an end-to-end reinforcement learning agent! It’s great to see all the positive feedback from gamers!

Sony AI

@SonyAI_global

10 months

Introducing #GTSophy to @thegranturismo players of all levels is a significant milestone for the Sony AI team and the evolution of Gran Turismo. Watch @GTPlanet take on Gran Turismo Sophy 2.0 in #GY7 .

7

31

160

0

13

126

Peter Stone

@PeterStone_TX

1 year

It's now well-known (and not surprising) that current LLMs have trouble generating correct plans that require real-world knowledge. Here's a possible solution. I'm very excited about this line of work!

Learning Agents Research Group

@utlarg

1 year

Can LLMs reliably solve long-horizon planning problems? LLM+P: Empowering Large Language Models with Optimal Planning Proficiency Link: Code:

2

9

74

2

12

92

Peter Stone

@PeterStone_TX

8 months

Honored to be a part of the inaugural RLC. Looking forward to it!

RL_Conference

@RL_Conference

8 months

Excited to announce our first RLC keynote speaker: @PeterStone_TX !

0

9

101

0

1

60

Peter Stone

@PeterStone_TX

9 months

'twas a beautiful day for a hike with (some of) my Learning Agents Research Group! @utlarg

0

2

55

Peter Stone

@PeterStone_TX

12 days

Proud that this paper was awarded the outstanding application paper at the conference!

Miguel Vasco

@omiguelvasco

14 days

Can we train vision-based reinforcement learning agents that achieve super-human performance against human players in racing games? Check out our latest work to be presented at @RL_Conference ! Paper: Website: A very fast 🧵(1/7)

1

10

34

2

4

54

Peter Stone

@PeterStone_TX

1 month

WisTex United won the RoboCup 2024 Standard Platform League "Challenge Shield" (lower division) competition. Collaboration with Josiah Hanna's lab at Wisconsin. Most exciting match was a 2nd half comeback (with some luck):

2

3

49

Peter Stone

@PeterStone_TX

14 days

Looking forward to my talk on Sunday afternoon!

Sony AI

@SonyAI_global

14 days

🚀 Sony AI will be at @RL_Conference 2024! Don't miss @PeterStone_TX 's keynote on practical RL insights. 🔗 Read more: #ReinforcementLearning #GranTurismo7

0

12

32

0

1

48

Peter Stone

@PeterStone_TX

28 days

Very excited about this work relating State Space Models (SSMs) to Online learning, and leading to a new, more efficient architecture!

Bo Liu

@cranialxix

29 days

How to design State Space Models (SSM) from principles? We propose to view SSM's recurrence as the per-step closed-form solution to an online learning problem. To this end, we present Longhorn, a novel SSM that achieves 1.8x better sampling efficiency against Mamba.

6

35

172

0

3

41

Peter Stone

@PeterStone_TX

2 years

Super proud of this accomplishment by my Sony AI team. Surely one of the broadest releases of an RL in a commercial product to date!

Zer0 to 5ive

@Zer0to5ive

2 years

Congratulations to team @SonyAI_global ! In just one year, they took their breakthrough AI agent #GTSophy from a research project to a commercial product. Learn more below ⬇️

0

10

0

2

40

Peter Stone

@PeterStone_TX

3 years

Thanks to Will Knight from Wired for this great description of our Sony AI project that appeared on today’s cover of Nature!

Sony AI

@SonyAI_global

3 years

We took @willknight for a ride through the creation of #GTSophy . Read the whole story on @WIRED

0

16

58

0

5

36

Peter Stone

@PeterStone_TX

1 year

Check out our RSS paper on training sensorimotor mobile manipulation policies with RL.

Jiaheng Hu

@JiahengHu1

1 year

Training sensorimotor Mobile Manipulation policies with RL is hard: many objectives (non-collision, reach…) and high DoF (arm, base, head…) CausalMoMa (, RSS23) makes it possible by leveraging causal dependencies between action dims and rewards.

1

23

124

0

6

37

Peter Stone

@PeterStone_TX

3 years

Congratulations to the students of the Learning Agents Research Group and colleagues at Sony AI for working with me on 9 papers to be presented at ICRA this week. Here are a few of them: (1/6)

1

0

36

Peter Stone

@PeterStone_TX

2 years

This will be a very fun talk. I encourage you to attend!

Sony AI

@SonyAI_global

2 years

Tomorrow, @PeterStone_TX , Executive Director of Sony AI America, will be giving a talk on "Outracing Champion 'Gran Turismo' Drivers with Deep Reinforcement Learning" at @UTAustin 's Forum for Artificial Intelligence. Learn how to tune in below. #GTSophy

0

6

20

0

3

34

Peter Stone

@PeterStone_TX

10 months

80% eclipse here in Austin

0

1

35

Peter Stone

@PeterStone_TX

1 year

It's been an honor to serve as chair of the AI 100 Standing Committee for the past 4 years! During my term, we released the 2021 report, recruited some great new members, and are completing an essay competition for your researchers in AI.

1

0

35

Peter Stone

@PeterStone_TX

1 year

Looking forward to visiting Alberta!

Amii

@AmiiThinks

1 year

Upper Bound presents @PeterStone_TX as a Keynote Speaker! He will talk about lessons on practical reinforcement learning from his time as the founder and director of the Learning Agents Research Group (LARG) at The University of Texas in Austin. #UpperBound2023 #ABTech #YEGTech

0

5

1

34

Peter Stone

@PeterStone_TX

1 year

I was interviewed on NPR this afternoon about the open letter posted by the Future of Life Institute.

An open letter signed by tech leaders, researchers proposes delaying AI development

NPR's Adrian Florido speaks with Peter Stone, computer science professor at the University of Texas, on an open letter calling for a temporary halt in development of advanced artificial intelligence.

www.npr.org

1

7

30

Peter Stone

@PeterStone_TX

2 years

I got a nice quote in this article. Looking forward to teaching in this program!

The New York Times

@nytimes

2 years

The University of Texas at Austin will start a large-scale, low-cost online Master of Science degree program in artificial intelligence, the institution announced. The new program could help swiftly expand the AI work force in the U.S.

25

80

366

1

30

Peter Stone

@PeterStone_TX

2 months

Kudos to the whole Sony AI team!

Sony AI Wins 2024 AI Breakthrough Award for Innovative Use of AI in Gaming – Sony AI

TOKYO – June 28, 2024 – Sony AI today announced that it has received the “Best Overall Use of AI in Gaming” award in the...

ai.sony

5

2

29

Peter Stone

@PeterStone_TX

6 months

Brad Knox is presenting two papers at AAAI today. 11:15am journal track: Reward (Mis)design for Autonomous Vehicles: Evening poster: Learning Optimal Advantage from Preferences and Mistaking it for Reward: @utlarg @UTCompSci

Learning Optimal Advantage from Preferences and Mistaking it for Reward

We consider algorithms for learning reward functions from human preferences over pairs of trajectory segments, as used in reinforcement learning from human feedback (RLHF). Most recent work...

arxiv.org

0

2

30

Peter Stone

@PeterStone_TX

1 year

The Ripon society published my editorial on the state of AI. I didn't choose the title, but otherwise, I like how it turned out. Comments more than welcome.

Memo to Washington: AI Needs Your Full Attention … Now! | The Ripon Society

The development and deployment of this one specific type of AI technology — large generative models such as GPT4 — is outpacing our ability to understand th ...

riponsociety.org

0

5

29

Peter Stone

@PeterStone_TX

1 year

Looking forward to offering this "AI Literacy" course to the whole UT Austin community this fall!

NaturalSciences @ UT

@TexasScience

1 year

Get up to speed on AI: what it can and can’t do & its societal implications. Take the new 1 credit-hour course “The Essentials of AI for Life and Society.” Open this fall to all @UTAustin students, faculty & staff. @UTCompSci @UTGoodSystems @undergrad_UT

0

3

14

0

1

28

Peter Stone

@PeterStone_TX

3 years

This article on using RL to learn pandemic response strategies was a productive collaboration between @SonyAI_global , @TexasScience , and @TAMUEngineering ! @UTGoodSystems @UTCompSci @utlarg @texas_robotics

J. AI Research-JAIR

@JAIR_Editor

3 years

New Article: "Agent-Based Markov Modeling for Improved COVID-19 Mitigation Policies" by Capobianco, Kompella, Ault, Sharon, Jong, Fox, Meyers, Wurman and Stone

0

3

12

0

9

28

Peter Stone

@PeterStone_TX

5 months

Last fall, along with Joydeep Biswas and Don Fussell, I created a 1-credit-hour course on "The Essentials of AI for Life and Society". The lecture videos are now all online:

CS 109: The Essentials of AI for Life and Society

The set of thirteen lectures on fundamental concepts for AI literacy, as well as the ethical and societal implications of AI technologies, were given by faculty from across the university. Recordings...

hr.utexas.edu

1

7

27

Peter Stone

@PeterStone_TX

3 years

Nice summary of progress in RL applicability by @jmac_ai

James

@jmac_ai

3 years

0

3

45

0

2

27

Peter Stone

@PeterStone_TX

3 months

I was honored to be featured on the first episode of this podcast. I'm pleased with how it turned out!

NaturalSciences @ UT

@TexasScience

3 months

What exactly is artificial intelligence, & how can we make sure it’s safe & useful? @PeterStone_TX in @UTCompSci answers these Qs & more on the first episode of the #AIForTheRestOfUs podcast. 🎧Listen: #TexasAI #YearofAI #Podcast #ArtificialIntelligence

2

11

28

1

0

27

Peter Stone

@PeterStone_TX

2 years

This paper at NeurIPS is a follow up on our GT Sophy superhuman agent at Gran Turismo

Learning Agents Research Group

@utlarg

2 years

Value Function Decomposition for Iterative Design of Reinforcement Learning Agents () James MacGlashan, Evan Archer, Alisa Devlic, Takuma Seno, Craig Sherstan, Peter Wurman, Peter Stone ( @PeterStone_TX ), @SonyAI_global Tu, Nov 29, 16:30 -Poster Session2

2

0

9

2

5

27

Peter Stone

@PeterStone_TX

2 years

RoboCup 2022 is about to begin. The standard platform league will be streaming here: #RoboCup2022 #robocup @utlarg @texas_robotics

RoboCup SPL

Welcome to the YouTube channel of the RoboCup Standard Platform League. RoboCup 2024: https://spl.robocup.org/call-for-participation-2024/ RoboCup 2023: https://spl.robocup.org/results-2023/ GORE...

www.youtube.com

1

10

25

Peter Stone

@PeterStone_TX

10 months

Thanks to Fox 7 for great coverage of our robot parade yesterday!

Robots on parade at UT Austin campus | FOX 7 Austin

Robots were on parade on UT Austin's campus Thursday. The event was an opportunity to showcase the technology being developed by the university's Texas Robot...

www.youtube.com

0

4

20

Peter Stone

@PeterStone_TX

1 year

Looking forward to visiting my friends in Edmonton!

0

24

Peter Stone

@PeterStone_TX

3 years

Check out our work on intrinsic motivation using adversarial distribution matching at NeurIPS. It is a core part of @IshanDurugkar ‘s dissertation research.

Ishan Durugkar @ NeurIPS-23

@IshanDurugkar

3 years

I'll be presenting this work with @mauriciogtec @scottniekum @PeterStone_TX at #NeurIPS2021 this week. Come by my poster between 8.30 am and 10 am PST on Friday the 10th.

0

2

28

0

6

23

Peter Stone

@PeterStone_TX

10 months

More good coverage of our robot parade from a couple of weeks ago: @texas_robotics

Students and Faculty Parade Their Robots Through Campus

A group of faculty and students marched from one end of Speedway to the other, as onlookers stopped — or followed — to take in a peculiar scene: a parade

news.utexas.edu

1

7

23

Peter Stone

@PeterStone_TX

2 years

Looking forward to seeing you there!

Richard Sutton

@RichardSSutton

2 years

My favorite conference is a small one: The Multi-disciplinary Conference on Reinforcement Learning and Decision Making. It works best if only those with a genuine interest in crossing disciplines attend.

5

49

502

0

2

23

Peter Stone

@PeterStone_TX

10 months

This sarcastic robot gives a tour of our building while interacting naturally with the user. A year or two ago this wouldn’t have been possible by anyone. Now it’s a (very successful!) undergraduate summer project!

Justin Hart

@justinhart

10 months

Dobby is a conversational service robot and the starting point of my lab's new work on LLMs in robotics! #livingwithrobotslab @PeterStone_TX @texas_robotics @UTCompSci

0

4

19

1

0

23

Peter Stone

@PeterStone_TX

2 years

Really looking forward to RLDM!

Matthew Gombolay

@MatthewGombolay

2 years

Thrilled to be an invited speaker at RLDM this June at one of my first in-person conferences as a Prof! Thanks to the program chairs ( @PeterStone_TX & Roshan Cools) for the invitation! Hope to see you all @BrownUniversity . @GTrobotics @core_robotics @gtcomputing

3

4

51

0

23

Peter Stone

@PeterStone_TX

11 months

When a robot does task and motion planning (TAMP), the symbolic state space (for task planning) ought to depend on the locations of objects at the motion planning level. This IROS paper addresses how to tailor the symbolic state space to the situation at hand.

Xiaohan Zhang

@XiaohanZhang220

11 months

S3O: Symbolic State Space Optimization tl;dr: Solving Task and Motion Planning problems without predefining task-level state space in mobile manipulation domains. w/ @yifengzhu_ut @yding25 @yuqian_jiang @yukez @PeterStone_TX @ShiqiZhang7 Check it out at @IROS2023 next week!

1

9

52

0

5

22

Peter Stone

@PeterStone_TX

4 years

Joint work with Yuchen Cui, Qiping Zhang, @bradknox , Alessandro Allievi, and @scottniekum

Sony AI

@SonyAI_global

4 years

Join @PeterStone_TX , Executive Director of #SonyAI America in a demonstration program at #AAAI2021 , "Demonstration of the EMPATHIC Framework for Task Learning from Implicit Human Feedback." Details on the research can be found here:

0

2

0

3

22

Peter Stone

@PeterStone_TX

1 month

A good first day of RoboCup matches for WisTex, a joint team between Josiah Hanna’s lab at Wisconsin and mine at UT Austin.

RoboCup SPL League

@RobocupSpl

1 month

Challenge Shield Round 2 WisTex United 6:0 Naova WisTex claimed its second victory in two matches with a resounding performance via Naova. Despite the result, the well-organized Naova defense put up a good fight, which should serve them well later in the tournament.

0

1

22

Peter Stone

@PeterStone_TX

3 years

RLDM is a very fun conference to attend - and is planned to be in person. Submit an extended abstract to present a poster. It’s non-archival, so work recently published or under review is fine - as long as it’s accessible to a broad audience.

Marc G. Bellemare

@marcgbellemare

3 years

Reminder - long abstracts for RLDM are due a week from now. See you in Providence?

0

5

37

0

1

22

Peter Stone

@PeterStone_TX

1 year

I couldn’t be leaving it in better hands!

Vincent Conitzer

@conitzer

1 year

Honored+awed to take over from the amazing @PeterStone_TX as chair of the #AI100 standing committee. Thanks to @erichorvitz &Mary Horvitz for their vision+funding for this 100yr study and the all-star cast of committee members for their time and expertise!

5

6

57

0

1

22

Peter Stone

@PeterStone_TX

2 years

@EugeneVinitsky Regarding research notebook, based on a research cent suggestion from a colleague, my group has been using a standard format of Goals, Accomplishment, Objectives, and Issues (GAOI). If interested, email me and I'll send the instructions I sent to my students. It's working well!

4

0

20

Peter Stone

@PeterStone_TX

2 years

Check out our article in Autonomous Robots on the ways in which ML is and isn’t useful for robot navigation.

Xuesu Xiao

@XuesuXiao

2 years

Navigation has been studied by roboticists for decades. Do you ever wonder why and how learning can help mobile robots navigate better? Read our Autonomous Robots article "Motion Planning and Control for Mobile Robot Navigation Using Machine Learning: a Survey" to find out more!

2

5

19

0

20

Peter Stone

@PeterStone_TX

2 years

@ylecun Good seeing you at NeurIPS! But I don't think the field should abandon any of these directions. AI and ML need different people exploring different approaches - for the same reason it was good not to abandon NNs when many people thought they were a dead end.

1

0

20

Peter Stone

@PeterStone_TX

1 year

It’s been an honor to serve as chair of the standing committee. #ai100

Erik Brynjolfsson

@erikbryn

1 year

Fascinating meeting of the Standing Committee meeting of the Hundred Study of AI today. Our new chair, @conitzer and our outgoing chair, @PeterStone_TX urged us to take the long-term view of AI’s impact on society. #AI100

5

2

30

1

0

21

Peter Stone

@PeterStone_TX

4 months

Proud to be a part of this fantastic department!

NaturalSciences @ UT

@TexasScience

5 months

Kudos to @UTCompSci ’s graduate program on climbing up a spot in the @USNews rankings! Details here: #USNewsRankings #UTCompSci #UTAustin

1

6

14

0

21

Peter Stone

@PeterStone_TX

2 years

Looking forward to talking about GT Sophy in a few hours at this workshop!

Noam Brown

@polynoamial

2 years

The #AAAI2022 RL in Games workshop starts Monday starting at 7am PT! We have a great lineup of speakers including @PeterStone_TX , @fangf07 , @karl_tuyls , and many great paper presentations!

0

6

26

0

2

19

Peter Stone

@PeterStone_TX

9 months

Check out Chen's paper at NeurIPS on revising RL policies to meet new constraints.

Chen Tang

@ChenTangMark

9 months

🌟Excited to present our paper () at #NeurIPS2023 next week! We introduce a novel RL framework, Residual Q-learning, to customize an imitative policy towards additional task requirements. Join us for the poster session on 13 Dec, 10:45 a.m. CST! 🧵

3

11

28

0

1

20

Peter Stone

@PeterStone_TX

3 years

What a touching event. Thanks @YesItsMeElad for organizing, @r_mirsky for posting, and so many current and former students for being there and for your moving tributes and memories!

0

1

18

Peter Stone

@PeterStone_TX

2 years

@scottniekum This is an important issue that will be fought by the university and in the legislature. The best chance of winning is by changing the electorate, which requires people coming to Texas, not leaving! TX Robotics and CS hiring too. (Glad you’re happy, but we miss you! :-) ).

2

4

18

Peter Stone

@PeterStone_TX

3 years

RoboCup 2021 starts in just a few days!

Sony AI

@SonyAI_global

3 years

We're excited to share a new blog, "RoboCup and Its Role in the History and Future of AI" by @PeterStone_TX , Executive Director #SonyAI America, Director @txRobot , and Professor at @UTCompSci . Discover the impact @robocup_org has had on #AI and #robotics .

1

12

20

0

2

18

Peter Stone

@PeterStone_TX

2 years

Calling for essays from early career AI researchers. The winner will be invited to participate in the next #AI100 study panel. (Yes, it's permissible to use LLMs as a tool, as long as it's acknowledged and you're prepared to stand behind your entry. See the rules for details.)

Stanford HAI

@StanfordHAI

2 years

How will AI affect work, life, and society in the future? The #AI100 publishes a report every five years seeking to answer this question. Now add your voice to the conversation in this newly launched essay competition:

1

14

25

0

11

19

Peter Stone

@PeterStone_TX

3 months

Excited about this paper advancing open-world imitation learning from observation!

Yifeng Zhu 朱毅枫

@yifengzhu_ut

3 months

Imagine bringing a personal robot home in the future. How fast can you teach it to do new tasks? We introduce ORION — now a robot can imitate manipulation from a single video demonstration!

5

50

268

0

2

18

Peter Stone

@PeterStone_TX

3 years

Thanks @omead_a for the tour of this very impressive facility. As @JCHartzell said, we're looking forward to working with you!

Jay Hartzell

@JCHartzell

3 years

Inspiring and impressive visit to see what @Tesla is doing in Austin. Peter Stone and I are excited to work with @omead_a and Tesla to build out what will clearly be an incredible partnership with @UTAustin . This is going to be huge, on so many levels! 🤘

9

35

248

0

3

19

Peter Stone

@PeterStone_TX

3 years

Check out @IshanDurugkar ’s work (with @mauriciogtec , @scottniekum and me) on learning an intrinsic reward via distribution matching to an idealized target policy state visitation distribution.

Ishan Durugkar @ NeurIPS-23

@IshanDurugkar

3 years

Excited to talk about Adversarial Intrinsic Motivation (AIM), accepted to NeurIPS 2021. It learns an intrinsic reward signal that guides the agent's exploration to find the goal in goal-conditioned reinforcement learning. See an example of the system in action below ... 1/🧵

3

26

160

0

3

18

Peter Stone

@PeterStone_TX

2 years

Just doing my part to reassure the local community that number five isn’t alive.

Good Systems

@UTGoodSystems

2 years

In response to recent news that a Google engineer claimed AI chatbot LaMDA had become sentient, @PeterStone_TX spoke with @fox7austin about #AI capabilities:

0

2

8

2

1

18

Peter Stone

@PeterStone_TX

2 years

@EugeneVinitsky Also, the number of hours really isn't the point. Work when you're most productive, and be efficient. Don't feel guilty about taking time off during the day when it's nice out. I learned early on that I could often get more done in 4 hours if I spent the first hour exercising.

1

0

17

Peter Stone

@PeterStone_TX

2 years

@hardmaru @slashML At Sony AI we are actively working on RL research. For example:

Gran Turismo Sophy

Gran Turismo Sophy's website. GT Sophy is a revolutionary superhuman racing AI agent that has been featured on the cover of the world's leading science journal, Nature. Project overview, innovative...

www.gran-turismo.com

1

0

18

Peter Stone

@PeterStone_TX

3 years

Thanks to KXAN for a very nice story on our new graduate student training program on ethical robots! @junfengjiao @texas_robotics @UTCompSci @UTGoodSystems @TexasScience @Joydeepb_robots @justinhart

New UT program puts focus on ethical AI, building robots to do ‘helpful tasks’

It’s a question students at the University of Texas at Austin will soon have to take a deeper look into.

www.kxan.com

0

3

16

Peter Stone

@PeterStone_TX

3 years

RoboCup 2021 ended up being a great success! More than 2,000 participants from around the world participated in a set of "remote" robotics competitions and symposium! @robocup_org 1/2

1

2

18

Peter Stone

@PeterStone_TX

3 years

I’m excited about this upcoming announcement on Wednesday!

Sony AI

@SonyAI_global

3 years

🏁 COMING SOON 🏁 On 2/9, our team is excited to launch our Gaming Flagship and announce a breakthrough project in #AI created through a collab with Polyphony Digital Inc. (PDI) and @Sony Interactive Entertainment (SIE). Enjoy this sneak peek.

19

152

514

0

1

16

Peter Stone

@PeterStone_TX

3 years

I’m excited about the upcoming release of the 2nd Study Panel report of the One Hundred Year Study on AI. Watch for it next week! @mlittmancs

Doug Richmond

@drphd2k7

3 years

#Artificialintelligence ... AI100: a discussion of the AI100 Report – virtual event September 28, two live broadcasts at 9-10a & 5-6p PT. Discussion leaders @Rbaltman , @PeterStone_TX , & @mlittmancs w/panel. @StanfordHAI #STEM #AI

0

2

4

0

1

16

Peter Stone

@PeterStone_TX

2 years

@EugeneVinitsky All sage advice - thanks for sharing! The main thing I see missing is self-care. It's a marathon, not a sprint. Maintain hobbies, get exercise, engage with your (non-university) community, make time for your significant other (or invest in finding someone).

1

0

15

Peter Stone

@PeterStone_TX

4 months

In response to a bunch of requests, the reading list for the course "Essentials of AI for Life and Society" is now online (along with the lecture videos):

0

4

16

Peter Stone

@PeterStone_TX

14 days

We catalog the real-world successes of deep RL across various robotic competencies, analyze the underlying trends with a new taxonomy of problem definitions & solution methods, and highlight critical challenges and key avenues of future work for roboticists and RL researchers.

1

3

19

Peter Stone

@PeterStone_TX

3 years

I think this interview turned out well. It was on KUT, Austin’s NPR station.

Texas Robotics

@texas_robotics

3 years

Could Playstations pave the way for new self-driving tech in cars? Peter Stone @PeterStone_TX , executive director of Sony AI America and director of Texas #Robotics , joins today's @TexasStandard broadcast to talk more about this project! Listen here:

1

8

0

15

Peter Stone

@PeterStone_TX

2 years

@ylecun Regarding MPC vs. RL, it sounds like you're advocating for model-based RL over model-free. I tend to agree, especially in robotics. But model-free RL outperforms MPC (so far) in simulated high-speed racing, which seems perfectly suited for MPC:

Gran Turismo Sophy

Gran Turismo Sophy's website. GT Sophy is a revolutionary superhuman racing AI agent that has been featured on the cover of the world's leading science journal, Nature. Project overview, innovative...

www.gran-turismo.com

1

14

Peter Stone

@PeterStone_TX

3 years

Very proud to be a part of this with @junfengjiao @Joydeepb_robots @justinhart and other great colleagues here at UT Austin.

Computer Science at UT Austin

@UTCompSci

3 years

@UTCompSci is introducing "CREATE," a graduate program prioritizing ethical artificial intelligence in robotics. Students will learn how to ethically design and develop service robots that will contribute to the future. Read more here:

0

7

12

0

14

Peter Stone

@PeterStone_TX

2 years

Totally agree. I guess I’m an old timer too. :-)

Thomas G. Dietterich

@tdietterich

2 years

@mezaoptimizer Old time AI people like me have always been working on AGI. We just called it AI. To me AGI is just a marketing term. We old timers think we know how hard the problem is, and we are lolling as the younger generation discovers this

14

18

163

0

14

Peter Stone

@PeterStone_TX

8 months

If you’re at NeurIPS, Come see Jiaheng and Zizhao at our poster!

Jiaheng Hu

@JiahengHu1

8 months

@duke_zzwang and I will be presenting ELDEN @ 14 Dec (Thurs) 10:45 - 12:45 #1423 at #NeurIPS2023 . Come by our poster to chat about unsupervised Reinforcement Learning and Causality!

0

5

14

0

14

Peter Stone

@PeterStone_TX

2 years

Check out our ICML paper on discovery of causal models for RL!

Zizhao Wang

@duke_zzwang

2 years

Want the dynamics model and model-based RL to generalize to unseen states? Causality is one of the keys! Our CDL is a new dynamics model - discovers causal dependencies from data - derives a versatile task-independent state abstraction ICML'22 paper: 1/n

3

8

58

0

1

14

Peter Stone

@PeterStone_TX

1 year

An exciting opportunity to take a leadership role at Sony AI on AI for gastronomy:

0

2

12

Peter Stone

@PeterStone_TX

3 years

Check out this new work on reward design for RL!

0

1

13

Peter Stone

@PeterStone_TX

14 days

To appear in the 2025 Annual Review of Control, Robotics, and Autonomous Systems: . Co-authors: @ChenTangMark , @babbatem , @JiahengHu1 , @rohanchandra30 , @RobobertoMM , @PeterStone_TX @UTAustin , @texas_robotics

0

15

Peter Stone

@PeterStone_TX

2 years

@natolambert @lvwerra @lcastricato @Dahoas1 @carperai Thanks for a very clear post on RLHF for LLMs. Note that RLHF in settings other than LLMs has been around for much longer than indicated, though. See, e.g., @bradknox 's TAMER work from 2008 and James MacGlashan's COACH. And then there was Deep TAMER for RLHF in deep learning..

1

2

12

Peter Stone

@PeterStone_TX

3 years

Congrats to my co-authors @XuesuXiao and @Joydeepb_robots on this fun advance to high-speed off-road navigation!

Learning Agents Research Group

@utlarg

3 years

Read about "Learning Inverse Kinodynamics for Accurate High-Speed Off-Road Navigation on Unstructured Terrain", which will appear in Robotics and Automation Letters (RAL). @XuesuXiao @Joydeepb_robots @PeterStone_TX @amrl_ut

1

4

9

0

13

Peter Stone

@PeterStone_TX

9 months

Excited about this work! I hope the community finds it useful.

Yifeng Zhu 朱毅枫

@yifengzhu_ut

9 months

Bo ( @cranialxix ) and I will be presenting LIBERO at #NeurIPS2023 . LIBERO is a robot learning benchmark for both lifelong and multitask learning research. We have many exciting follow-ups based on LIBERO. Look forward to chatting about them more at the conference!

1

9

59

0

12

Peter Stone

@PeterStone_TX

2 years

That’s a blurry picture of me (and @scottniekum ) in the background.

Computer Science at UT Austin

@UTCompSci

2 years

@UTAustin has officially established a new online learning master’s program in artificial intelligence (AI), with the potential to bring thousands of new students into the field. To read more, visit

0

6

31

0

12

Peter Stone

@PeterStone_TX

1 year

@johnjnay @UTAustin We're very excited about this line of work - connecting LLMs to optimal planners.

2

0

10

Peter Stone

@PeterStone_TX

4 months

This is our take on the important current priorities for AI research, policy, and practice.

Eric Horvitz

@erichorvitz

5 months

"Now, Later, and Lasting: 10 Priorities for AI Research, Policy, and Practice," forthcoming in CACM, with @conitzer @SheilaMcIlraith @PeterStone_TX #AI100 @CACMmag @TheOfficialACM @StanfordHAI @PartnershipAI @WHOSTP @CarnegieMellon @UofT @CIFAR_News

2

18

61

0

11

Peter Stone

@PeterStone_TX

2 years

I recently spoke about the state of AI and how machine learning techniques are closing the gap between autonomous systems and humans in competitions at @EON_events – The Applied Artificial Intelligence Event. Check out more about #EON2022 at .

0

4

10

Peter Stone

@PeterStone_TX

3 years

The interview turned out quite nicely! @utlarg @texas_robotics @SonyAI_global @UTCompSci

RoboCup Federation

@robocup_org

3 years

#BBCNews article that highlights RoboCup - our goals and contributions and includes an interview with RoboCup President, Prof. Peter Stone:

0

1

13

0

1

10

Peter Stone

@PeterStone_TX

3 years

Thanks @AmulyaYadav19 for inviting me. It was an honor to be a keynote speaker at the workshop.

Amulya Yadav

@AmulyaYadav19

3 years

Fascinating talk by @PeterStone_TX at the Workshop on Autonomous Agents for Social Good (AASG 21) @aamas2021 . Thank you Peter! Looking forward to another exciting talk by Tuomas Sandholm later in the day!

0

6

0

1

11

Peter Stone

@PeterStone_TX

3 years

Huge kudos to @mlittmancs and the whole 2021 Study Panel for authoring a fantastic report!

Eric Horvitz

@erichorvitz

3 years

Milestone report out: 100 Yr Study on AI Expert panel assesses state of #AI & directions fwd @mlittmancs @PeterStone_TX @SheilaMcIlraith @marylgray @robotsmarts @Rbaltman @percyliang @ghadfield @MelMitchell1 @FinaleDoshi @CraigBoutilier @isbellHFh #AI100

3

39

87

0

2

10

Peter Stone

@PeterStone_TX

2 years

This work led by @bradknox makes an important observation about how to learn reward functions aligned with human preferences.

0

1

11

Peter Stone

@PeterStone_TX

10 months

I hope this will be a very useful benchmark for lifelong robot learning!

Yifeng Zhu 朱毅枫

@yifengzhu_ut

10 months

We are thrilled to announce LIBERO, a lifelong robot learning benchmark to study knowledge transfer in decision-making and robotics at scale! 🤖 LIBERO paves the way for prototyping algorithms that allow robots to continually learn! More explanations and links are in the 🧵

2

57

243

0

1

10

Peter Stone

@PeterStone_TX

2 years

Hope to see many of you there!

Sony AI

@SonyAI_global

2 years

This week, we're excited to be a sponsor at the 5th Multi-disciplinary Conference on Reinforcement Learning and Decision Making where @PeterStone_TX , Sony AI America Executive Director, is serving as a program chair. Registration is still open. #RLDM2022

0

1

16

0

3

10

Peter Stone

@PeterStone_TX

3 years

Today we will be presenting a paper that uses this simulator to examine strategies for contact tracing at the AAMAS conference:

Sony AI

@SonyAI_global

3 years

Created by @PeterStone_TX and team, the #Pandemic Simulator is an #opensource , agent-based simulator that applies #reinforcementlearning to optimize and increase the understanding of how best to mitigate the spread of pandemics #COVID19

0

2

0

1

10

Peter Stone

@PeterStone_TX

2 years

This is fun work to be presented by @hareshmiriyala at IROS next month.

0

9

Peter Stone

@PeterStone_TX

1 year

Thanks, @AjanovicZlatan for organizing the workshop and for inviting me!

Zlatan Ajanović @ RSS 2024

@AjanovicZlatan

1 year

@PeterStone_TX opening our #L3H2 #ICRA2023 workshop with inspiring topic and origins of #RLHF learning methods. @ieee_ras_icra

0

1

3

1

0

10

Peter Stone

@PeterStone_TX

1 year

@conitzer I won’t speak for the whole RoboCup community here, but personally I think their paper connects very well to past work and acknowledges the limitations compared to RoboCup teams including that they use off board global sensing. Overall, I think it’s fun, we’ll-executed work.

0

9

Peter Stone

@PeterStone_TX

4 years

Welcome to Sony AI, @alicexiang !

Alice Xiang

@alicexiang

4 years

I am excited to announce that I started a new position today as a Senior Research Scientist at Sony AI! I will be working to build out their responsible AI practice. (1/4)

10

4

377

1

0

9

Peter Stone

@PeterStone_TX

2 years

This is a very general approach to the very common problem of bilevel optimization.

Learning Agents Research Group

@utlarg

2 years

BOME! Bilevel Optimization Made Easy: A Simple First-Order Approach () Bo Liu( @cranialxix ), Mao Ye, Stephen Wright, Peter Stone( @PeterStone_TX ), Qiang Liu We, Nov 30, 16:30 -- Poster Session 4

2

1

5

1

2

9

Peter Stone

@PeterStone_TX

10 months

Check out our NeurIPS paper on efficient exploration in domains with complex dependencies.

Zizhao Wang

@duke_zzwang

10 months

Tasks at home can involve many objects with complex interdependencies, e.g., the butter needs to be melted on the stove before it can be mixed and fried with meat in a pot. How can RL efficiently explore such tasks with sparse rewards? Introducing our #NeurIPS23 paper ELDEN: 🧵